Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Fix checksumming regressions, from Tom Herbert.

 2) Undo unintentional permissions changes for SCTP rto_alpha and
    rto_beta sysfs knobs, from Denial Borkmann.

 3) VXLAN, like other IP tunnels, should advertize it's encapsulation
    size using dev->needed_headroom instead of dev->hard_header_len.
    From Cong Wang.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  net: sctp: fix permissions for rto_alpha and rto_beta knobs
  vxlan: Checksum fixes
  net: add skb_pop_rcv_encapsulation
  udp: call __skb_checksum_complete when doing full checksum
  net: Fix save software checksum complete
  net: Fix GSO constants to match NETIF flags
  udp: ipv4: do not waste time in __udp4_lib_mcast_demux_lookup
  vxlan: use dev->needed_headroom instead of dev->hard_header_len
  MAINTAINERS: update cxgb4 maintainer

MAINTAINERS

@@ -2594,7 +2594,7 @@ S:	Supported
 F:	drivers/infiniband/hw/cxgb3/
 
 CXGB4 ETHERNET DRIVER (CXGB4)
-M:	Dimitris Michailidis <dm@chelsio.com>
+M:	Hariprasad S <hariprasad@chelsio.com>
 L:	[email protected]
 W:	http://www.chelsio.com
 S:	Supported

drivers/net/vxlan.c

@@ -1156,15 +1156,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	if (!vs)
 		goto drop;
 
-	/* If the NIC driver gave us an encapsulated packet
-	 * with the encapsulation mark, the device checksummed it
-	 * for us. Otherwise force the upper layers to verify it.
-	 */
-	if ((skb->ip_summed != CHECKSUM_UNNECESSARY && skb->ip_summed != CHECKSUM_PARTIAL) ||
-	    !skb->encapsulation)
-		skb->ip_summed = CHECKSUM_NONE;
-
-	skb->encapsulation = 0;
+	skb_pop_rcv_encapsulation(skb);
 
 	vs->rcv(vs, skb, vxh->vx_vni);
 	return 0;
@@ -1201,6 +1193,7 @@ static void vxlan_rcv(struct vxlan_sock *vs,
 	skb_reset_mac_header(skb);
 	skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev)));
 	skb->protocol = eth_type_trans(skb, vxlan->dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	/* Ignore packet loops (and multicast echo) */
 	if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
@@ -2247,9 +2240,9 @@ static void vxlan_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
 	if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
-		dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
 	else
-		dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = free_netdev;
@@ -2646,8 +2639,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 		if (!tb[IFLA_MTU])
 			dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 
-		/* update header length based on lower device */
-		dev->hard_header_len = lowerdev->hard_header_len +
+		dev->needed_headroom = lowerdev->hard_header_len +
 				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 	} else if (use_ipv6)
 		vxlan->flags |= VXLAN_F_IPV6;

include/linux/netdev_features.h

@@ -117,6 +117,7 @@ enum {
 #define NETIF_F_GSO_IPIP	__NETIF_F(GSO_IPIP)
 #define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
+#define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
 #define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)

include/linux/netdevice.h

@@ -3305,6 +3305,13 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_IPIP    != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_MPLS    != (NETIF_F_GSO_MPLS >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }

include/linux/skbuff.h

@@ -338,17 +338,18 @@ enum {
 
 	SKB_GSO_GRE = 1 << 6,
 
-	SKB_GSO_IPIP = 1 << 7,
+	SKB_GSO_GRE_CSUM = 1 << 7,
 
-	SKB_GSO_SIT = 1 << 8,
+	SKB_GSO_IPIP = 1 << 8,
 
-	SKB_GSO_UDP_TUNNEL = 1 << 9,
+	SKB_GSO_SIT = 1 << 9,
 
-	SKB_GSO_MPLS = 1 << 10,
+	SKB_GSO_UDP_TUNNEL = 1 << 10,
 
 	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
 
-	SKB_GSO_GRE_CSUM = 1 << 12,
+	SKB_GSO_MPLS = 1 << 12,
+
 };
 
 #if BITS_PER_LONG > 32
@@ -1853,6 +1854,18 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
 	return pskb_may_pull(skb, skb_network_offset(skb) + len);
 }
 
+static inline void skb_pop_rcv_encapsulation(struct sk_buff *skb)
+{
+	/* Only continue with checksum unnecessary if device indicated
+	 * it is valid across encapsulation (skb->encapsulation was set).
+	 */
+	if (skb->ip_summed == CHECKSUM_UNNECESSARY && !skb->encapsulation)
+		skb->ip_summed = CHECKSUM_NONE;
+
+	skb->encapsulation = 0;
+	skb->csum_valid = 0;
+}
+
 /*
  * CPUs often take a performance hit when accessing unaligned memory
  * locations. The actual performance hit varies, it can be small if the

include/net/udp.h

@@ -111,7 +111,9 @@ struct sk_buff;
  */
 static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb)
 {
-	return __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov);
+	return (UDP_SKB_CB(skb)->cscov == skb->len ?
+		__skb_checksum_complete(skb) :
+		__skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov));
 }
 
 static inline int udp_lib_checksum_complete(struct sk_buff *skb)

net/core/datagram.c

@@ -739,22 +739,38 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 	__sum16 sum;
 
 	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
-	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !sum &&
-	    !skb->csum_complete_sw)
-		netdev_rx_csum_fault(skb->dev);
-
-	/* Save checksum complete for later use */
-	skb->csum = sum;
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb->csum_complete_sw = 1;
-
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+	skb->csum_valid = !sum;
 	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
 
 __sum16 __skb_checksum_complete(struct sk_buff *skb)
 {
-	return __skb_checksum_complete_head(skb, skb->len);
+	__wsum csum;
+	__sum16 sum;
+
+	csum = skb_checksum(skb, 0, skb->len, 0);
+
+	/* skb->csum holds pseudo checksum */
+	sum = csum_fold(csum_add(skb->csum, csum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+
+	/* Save full packet checksum */
+	skb->csum = csum;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb->csum_complete_sw = 1;
+	skb->csum_valid = !sum;
+
+	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete);
 

net/core/skbuff.c

@@ -689,6 +689,9 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->ooo_okay		= old->ooo_okay;
 	new->no_fcs		= old->no_fcs;
 	new->encapsulation	= old->encapsulation;
+	new->encap_hdr_csum	= old->encap_hdr_csum;
+	new->csum_valid		= old->csum_valid;
+	new->csum_complete_sw	= old->csum_complete_sw;
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif

net/ipv4/udp.c

@@ -1861,6 +1861,10 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
 	struct udp_hslot *hslot = &udp_table.hash[slot];
 
+	/* Do not bother scanning a too big list */
+	if (hslot->count > 10)
+		return NULL;
+
 	rcu_read_lock();
 begin:
 	count = 0;

net/sctp/sysctl.c

@@ -34,6 +34,8 @@
  *    Sridhar Samudrala     <[email protected]>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <net/sctp/structs.h>
 #include <net/sctp/sctp.h>
 #include <linux/sysctl.h>
@@ -46,6 +48,11 @@ static int sack_timer_min = 1;
 static int sack_timer_max = 500;
 static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */
 static int rwnd_scale_max = 16;
+static int rto_alpha_min = 0;
+static int rto_beta_min = 0;
+static int rto_alpha_max = 1000;
+static int rto_beta_max = 1000;
+
 static unsigned long max_autoclose_min = 0;
 static unsigned long max_autoclose_max =
 	(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
@@ -64,6 +71,9 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp,
 				loff_t *ppos);
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos);
 static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp,
 			     loff_t *ppos);
@@ -126,15 +136,19 @@ static struct ctl_table sctp_net_table[] = {
 		.procname	= "rto_alpha_exp_divisor",
 		.data		= &init_net.sctp.rto_alpha,
 		.maxlen		= sizeof(int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_alpha_min,
+		.extra2		= &rto_alpha_max,
 	},
 	{
 		.procname	= "rto_beta_exp_divisor",
 		.data		= &init_net.sctp.rto_beta,
 		.maxlen		= sizeof(int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_beta_min,
+		.extra2		= &rto_beta_max,
 	},
 	{
 		.procname	= "max_burst",
@@ -403,6 +417,16 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	pr_warn_once("Changing rto_alpha or rto_beta may lead to "
+		     "suboptimal rtt/srtt estimations!\n");
+
+	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+}
+
 static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp,
 			     loff_t *ppos)